agentleFS
Sign inStart free
fmindfmind/dot/skills/repository-docs/SKILL.md

repository-docs

Skill13 starsChanged 4 days agoMITView on GitHub

Write and sync README, AGENTS.md, and repo docs with verified behavior.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep human and agent documentation aligned with the implementation, with one canonical owner for every claim.

    line 15
  2. Distinctive:

    Choose the audience: use README guidance for project identity, proof of value, and the first successful use, adapting its starter for new …

    line 21
  3. Distinctive:

    Update canonical owners: keep setup and usage in human docs, agent commands and invariants in AGENTS.md, and reusable procedures in skills.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Repository Documentation

Keep human and agent documentation aligned with the implementation, with one canonical owner for every claim.

Workflow

  1. Inventory: locate README.md, root and nested AGENTS.md, docs/, community files such as .github/SECURITY.md, generated help, and .agents/skills/*/SKILL.md; include any additional catalog declared by the repository.
  2. Trace behavior: compare documentation with entry points, source, tests, manifests, mise tasks, hooks, CI, and current --help; verify paths, options, versions, examples, and supported behavior.
  3. Choose the audience: use README guidance for project identity, proof of value, and the first successful use, adapting its starter for new projects; add README assets for SVG logos, illustrations, and badges. Use AGENTS guidance for commands, constraints, invariants, and layout.
  4. Update canonical owners: keep setup and usage in human docs, agent commands and invariants in AGENTS.md, and reusable procedures in skills; link instead of copying.
  5. Verify: run the repository's documentation gate, dot agent context --check after editing AGENTS.md or skill metadata, lychee --include-fragments=full <files> for links, anchors, and #:~:text= fragments (a bare --include-fragments checks anchors only; add --include-verbatim when URLs in code carry claims, then dismiss placeholder hosts), dprint check for markup, and the site build where applicable; inspect rendered pages after layout changes.
  6. Report: name what changed, the source evidence and checks, and any external workflow or claim that remains unverified.

Gotchas

  • Edit generated documentation at its source: regenerate it; never hand-edit generated output or rewrite published history as cleanup.
  • Report each status claim separately: setup, tests, hosted CI, deployment, and publication are separate claims.
  • Documentation work authorizes relevant reversible edits: committing, publishing, or contacting others follows the current task authority.
  • Preserve conventions; exclude secrets: preserve repository conventions, public anchors, and the author's voice; never include secrets or transient session state.
  • Default to portable Markdown: where no convention exists, number every ordered item 1. so reordering never needs renumbering, tag code fences with a language, keep each paragraph on one line, use relative or ~-relative paths in skills and AGENTS.md, and start comment-capable configs with their official docs URL below any schema directive.

Documentation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free